{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FCNULDSNLPSIQSX3MCL6E2EIG2","short_pith_number":"pith:FCNULDSN","schema_version":"1.0","canonical_sha256":"289b458e4d5be4884afb6097e2688836ab07ad2b5797d2fd23061e52579d2dcd","source":{"kind":"arxiv","id":"2404.15790","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Large Language Models for Multimodal Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnab Dhua, Michael Huang, Oriol Barbany, Xinliang Zhu","submitted_at":"2024-04-24T10:30:42Z","abstract_excerpt":"Multimodal search has become increasingly important in providing users with a natural and effective way to ex-press their search intentions. Images offer fine-grained details of the desired products, while text allows for easily incorporating search modifications. However, some existing multimodal search systems are unreliable and fail to address simple queries. The problem becomes harder with the large variability of natural language text queries, which may contain ambiguous, implicit, and irrelevant in-formation. Addressing these issues may require systems with enhanced matching capabilities"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.15790","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-24T10:30:42Z","cross_cats_sorted":[],"title_canon_sha256":"041a29c1fda20d57e0d07f53c8753f936fcff0c2ab009dc2c88e02e02fc26606","abstract_canon_sha256":"5b54e12708155d3062dd1427b229b6c972114deee7fd3cd31aac1ff9472abea4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:45.234102Z","signature_b64":"anDx233GfObGO3g4Y+O91sFENJY9/4AG46Pd+nvY4Rj+RISkXYEPycWDMAme+jF2InA5m4lFLizxTpLlHStPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"289b458e4d5be4884afb6097e2688836ab07ad2b5797d2fd23061e52579d2dcd","last_reissued_at":"2026-07-05T08:11:45.233660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:45.233660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models for Multimodal Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnab Dhua, Michael Huang, Oriol Barbany, Xinliang Zhu","submitted_at":"2024-04-24T10:30:42Z","abstract_excerpt":"Multimodal search has become increasingly important in providing users with a natural and effective way to ex-press their search intentions. Images offer fine-grained details of the desired products, while text allows for easily incorporating search modifications. However, some existing multimodal search systems are unreliable and fail to address simple queries. The problem becomes harder with the large variability of natural language text queries, which may contain ambiguous, implicit, and irrelevant in-formation. Addressing these issues may require systems with enhanced matching capabilities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15790","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.15790/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.15790","created_at":"2026-07-05T08:11:45.233725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15790v1","created_at":"2026-07-05T08:11:45.233725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15790","created_at":"2026-07-05T08:11:45.233725+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCNULDSNLPSI","created_at":"2026-07-05T08:11:45.233725+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCNULDSNLPSIQSX3","created_at":"2026-07-05T08:11:45.233725+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCNULDSN","created_at":"2026-07-05T08:11:45.233725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2","json":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2.json","graph_json":"https://pith.science/api/pith-number/FCNULDSNLPSIQSX3MCL6E2EIG2/graph.json","events_json":"https://pith.science/api/pith-number/FCNULDSNLPSIQSX3MCL6E2EIG2/events.json","paper":"https://pith.science/paper/FCNULDSN"},"agent_actions":{"view_html":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2","download_json":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2.json","view_paper":"https://pith.science/paper/FCNULDSN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15790&json=true","fetch_graph":"https://pith.science/api/pith-number/FCNULDSNLPSIQSX3MCL6E2EIG2/graph.json","fetch_events":"https://pith.science/api/pith-number/FCNULDSNLPSIQSX3MCL6E2EIG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2/action/storage_attestation","attest_author":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2/action/author_attestation","sign_citation":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2/action/citation_signature","submit_replication":"https://pith.science/pith/FCNULDSNLPSIQSX3MCL6E2EIG2/action/replication_record"}},"created_at":"2026-07-05T08:11:45.233725+00:00","updated_at":"2026-07-05T08:11:45.233725+00:00"}